Instructions to use danelcsb/daniel-lfm2-350m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use danelcsb/daniel-lfm2-350m with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="danelcsb/daniel-lfm2-350m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("danelcsb/daniel-lfm2-350m")
model = AutoModelForCausalLM.from_pretrained("danelcsb/daniel-lfm2-350m", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use danelcsb/daniel-lfm2-350m with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use danelcsb/daniel-lfm2-350m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "danelcsb/daniel-lfm2-350m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "danelcsb/daniel-lfm2-350m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/danelcsb/daniel-lfm2-350m

SGLang

How to use danelcsb/daniel-lfm2-350m with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "danelcsb/daniel-lfm2-350m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "danelcsb/daniel-lfm2-350m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "danelcsb/daniel-lfm2-350m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "danelcsb/daniel-lfm2-350m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use danelcsb/daniel-lfm2-350m with Docker Model Runner:
```
docker model run hf.co/danelcsb/daniel-lfm2-350m
```

daniel-lfm2-350m / README.md

danelcsb

Retrain Daniel OS with profile and evidence routing

c3b478a verified 17 days ago

preview code

Raw

History Blame Contribute Delete

1.51 kB

	---
	base_model: LiquidAI/LFM2-350M
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- lfm2
	- peft
	- portfolio-assistant
	- grounded-generation
	license: other
	license_name: lfm1.0
	license_link: https://huggingface.co/LiquidAI/LFM2-350M/blob/main/LICENSE
	---

	# Daniel OS LFM2-350M

	Personalized LFM2-350M checkpoint for Sangbum Daniel Choi's browser-native
	portfolio assistant. The model was adapted with LoRA and merged for deployment.

	## Scope behavior

	The training set contains 296 curated conversations:

	- Verified-profile answers: 177
	- Evidence-grounded definitions: 12
	- Public-retrieval decisions: 15
	- Explicitly missing profile facts: 58
	- Privacy and safety refusals: 34

	Training data revision: `e54fa0460fd6e2e3c4c077607bfb79184d94fbdb`

	The assistant is trained to separate Daniel-specific claims from general
	definitions. It synthesizes definitions only from retrieved evidence, emits a
	public-search tool request when evidence is missing, and never claims to be Daniel.

	## Held-out behavioral evaluation

	- Overall: 84.4%
	- Verified-profile answers: 81.8%
	- Evidence-grounded definitions: 100.0%
	- Retrieval decisions: 75.0%
	- Missing-profile facts: 75.0%
	- Privacy and safety refusals: 100.0%

	The website supplies focused verified profile context and recent conversation
	history to this model. Privacy boundaries, visitor-identity handling, career
	chronology, and contextual follow-up behavior are learned from the SFT data
	rather than returned as fixed JavaScript answers.